MiniMax M2.5/M2.7 — B300 vs GB200 NVL72
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB200 NVL72 (NVIDIA Blackwell) on MiniMax M2.5/M2.7. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
Near the low end of the 31–180 tok/s/user interactivity band, at 68 tok/s/user on MiniMax M2.5/M2.7: B300 runs 6832 tok/s/GPU at $0.10/M tokens, GB200 NVL72 runs 8433 at $0.07/M. GB200 NVL72 is 32% cheaper per token; GB200 NVL72 delivers 23% more tok/s/GPU.
Setting 105 tok/s/user as the target on MiniMax M2.5/M2.7, B300 produces 3089 tok/s/GPU ($0.21 per million tokens) and GB200 NVL72 produces 3247 ($0.19). GB200 NVL72 is 10% cheaper per token; GB200 NVL72 delivers 5% more tok/s/GPU.
At 143 tok/s/user interactivity on MiniMax M2.5/M2.7, B300 delivers 1148 tok/s/GPU at $0.57 per million tokens; GB200 NVL72 delivers 1066 tok/s/GPU at $0.58. B300 is 3% cheaper per token; B300 delivers 8% more tok/s/GPU at this point. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B300:6832.4GB200 NVL72:8432.8 | B300:3089.2GB200 NVL72:3246.9 | B300:1148.3GB200 NVL72:1066.4 |
| Cost ($/M tok) | B300:$0.096GB200 NVL72:$0.073 | B300:$0.210GB200 NVL72:$0.190 | B300:$0.566GB200 NVL72:$0.581 |
| tok/s/MW | B300:3148586GB200 NVL72:4015616 | B300:1423572GB200 NVL72:1546138 | B300:529184GB200 NVL72:507786 |
| Concurrency | B300:~349GB200 NVL72:~928 | B300:~146GB200 NVL72:~236 | B300:~7GB200 NVL72:~45 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.